Description

You will design and implement Retrieval Augmented Generation (RAG) architectures, optimizing LLMs and managing AI model performance in regulated environments.

This role is on-site.

Responsibilities

• Architect and implement RAG pipelines using vector databases and embedding models.
• Engineer prompts and optimize LLM inference for pharmacovigilance and drug safety applications.
• Monitor, evaluate, and tune AI model performance against E2B and regulatory standards.
• Provision and configure Azure foundation services, managing Dev/Test/Prod subscriptions and governance controls.
• Coordinate with infrastructure teams to support deployment and environment management.

Required Skills

• 10+ years of experience in AI/ML engineering and software development.
• Deep expertise in RAG architecture, prompt engineering, and LLM optimization.
• Proficiency with AI/ML frameworks: PyTorch, TensorFlow, and LangChain.
• Strong experience with Azure Foundation Platform and cloud resource provisioning.
• Knowledge of pharmacovigilance, drug safety processes, and E2B standards.
• Understanding of regulatory compliance (FDA, EMA) in AI contexts.
• Experience with vector databases and embedding models.

Preferred Skills

• Experience coordinating with infrastructure teams for Azure resource management.

Key Skills

Education

Any Graduate